Advertisement

Predicting delay discounting from heterogeneous social media data

  • Tao Ding
  • Warren K. Bickel
  • Shimei PanEmail author
Original Article
  • 39 Downloads

Abstract

Delay discounting, a behavioral measure of impulsivity, is often used to quantify the human tendency to choose a smaller, sooner reward (e.g., $1 today) over a larger, later reward ($2 tomorrow). Delay discounting and its relation to human decision-making is a hot topic in economics and behavior science since pitting the demands of long-term goals against short-term desires is among the most difficult tasks in human decision-making (Hirsh et al. in J Res Personal 42:1646, 2008). Previously, questionnaire-based surveys were used to assess someone’s delay discounting rate (DDR). In this research, we develop a computational model to automatically predict DDR from diverse types of social media data such as likes and posts. We explore different unsupervised feature learning methods to take advantage of a large amount of unsupervised social media data. Based on our evaluation, the best model learned from social media likes achieved 0.634 ROC AUC, which 18% better than the baseline model that did not use unsupervised feature learning. The best model learned from social media posts achieved 0.641 ROC AUC, which is 24% better than the baseline that did not use unsupervised feature learning. We also employed unsupervised feature fusion to combine heterogeneous user data such as likes and posts together to further improve system performance. The final combined model outperformed the baseline that did not use unsupervised feature learning by 30%. Finally, we conducted additional analysis to uncover interesting correlation patterns between a person’s social media behavior and his/her DDR.

Keywords

Unsupervised feature learning Delay discounting Computational social science Social media 

Notes

References

  1. Alessi S, Petry N (2003) Pathological gambling severity is associated with impulsivity in a delay discounting procedure. Behav Process 64(3):345–354CrossRefGoogle Scholar
  2. Andrade LF, Petry NM (2014) White problem gamblers discount delayed rewards less steeply than their african american and hispanic counterparts. Psychol Addict Behav 28(2):599CrossRefGoogle Scholar
  3. Andrew G, Arora R, Bilmes JA, Livescu K (2013) Deep canonical correlation analysis. In: ICML, no 3, pp 1247–1255Google Scholar
  4. Angeletos GM, Laibson D, Repetto A, Tobacman J, Weinberg S (2001) The hyperbolic consumption model: calibration, simulation, and empirical evaluation. J Econ Perspect 15(3):47–68CrossRefGoogle Scholar
  5. Ayduk O, Mendoa-Denton R, Mischel W, Downey G, Peake P, Rodriguez M (2000) Regulating the interpresonal self: strategic self-regulation for coping with rejection sensitivity. Personal Soc Psychol 79(5):776–792CrossRefGoogle Scholar
  6. Baroni M, Dinu G, Kruszewski G (2014) Don’t count, predict! a systematic comparison of context-counting vs. context-predicting semantic vectors. In: ACL, no 1, pp 238–247Google Scholar
  7. Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828CrossRefGoogle Scholar
  8. Benton A, Arora R, Dredze M (2016) Learning multiview embeddings of Twitter users. In: Proceedings of the 54th annual meeting of the association for computational linguistics, vol 2, pp 14–19Google Scholar
  9. Bickel WK, Marsch LA (2001) Toward a behavioral economic understanding of drug dependence: delay discounting processes. Addiction 96(1):73–86CrossRefGoogle Scholar
  10. Bickel WK, Odum AL, Madden GJ (1999) Impulsivity and cigarette smoking: delay discounting in current, never, and ex-smokers. Psychopharmacology 146(4):447–454CrossRefGoogle Scholar
  11. Bickel WK, Yi R, Landes RD, Hill PF, Baxter C (2011) Remember the future: working memory training decreases delay discounting among stimulant addicts. Biological psychiatry 69(3):260–265CrossRefGoogle Scholar
  12. Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3(Jan):993–1022zbMATHGoogle Scholar
  13. Chaudhuri K, Kakade SM, Livescu K, Sridharan K (2009) Multi-view clustering via canonical correlation analysis. In: Proceedings of the 26th annual international conference on machine learning. ACM, pp 129–136Google Scholar
  14. Chen J, Hsieh G, Mahmud J, Nichols J (2014) Understanding individuals’ personal values from social media word use. In: Computer supported cooperative work, CSCW ’14, Baltimore, MD, USA, 15–19 February, 2014, pp 405–414Google Scholar
  15. Chirumbolo A, Leone L (2010) Personality and politics: the role of the hexaco model of personality in predicting ideology and voting. Personal Individ Differ 49(1):43–48CrossRefGoogle Scholar
  16. Coppersmith G, Dredze M, Harman C, Hollingshead K, Mitchell M (2015) Clpsych 2015 shared task: Depression and ptsd on twitter. In: Proceedings of the 2nd workshop on computational linguistics and clinical psychology: from linguistic signal to clinical reality, pp 31–39Google Scholar
  17. De Choudhury M, Gamon M, Counts S, Horvitz E (2013) Predicting depression via social media. In: ICWSM, vol 13, pp 1–10Google Scholar
  18. De Lathauwer L, De Moor B, Vandewalle J (2000) A multilinear singular value decomposition. SIAM J Matrix Anal Appl 21(4):1253–1278MathSciNetCrossRefGoogle Scholar
  19. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: CVPR09Google Scholar
  20. Ding T, Bickel WK, Pan S (2017) Multi-view unsupervised user feature embedding for social media-based substance use prediction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2275–2284Google Scholar
  21. Ding T, Bickel W, Pan S (2017) Multi-view unsupervised user feature embedding for social media-based substance use prediction. In: EMNLP, pp 2275–2284Google Scholar
  22. Ding T, Pan S (2016) Personalized emphasis framing for persuasive message generation. In: EMNLPGoogle Scholar
  23. Dixon MR, Marley J, Jacobs EA (2003) Delay discounting by pathological gamblers. J Appl Behav Anal 36(4):449–458CrossRefGoogle Scholar
  24. Du W, Green L, Myerson J (2002) Cross-cultural comparisons of discounting delayed and probabilistic rewards. Psychol Rec 52(4):479CrossRefGoogle Scholar
  25. Estle SJ, Green L, Myerson J, Holt DD (2007) Discounting of monetary and directly consumable rewards. Psychol Sci 18(1):58–63CrossRefGoogle Scholar
  26. Field M, Christiansen P, Cole J, Goudie A (2007) Delay discounting and the alcohol stroop in heavy drinking adolescents. Addiction 102(4):579–586CrossRefGoogle Scholar
  27. Giota KG, Kleftaras G (2013) The role of personality and depression in problematic use of social networking sites in greece. Cyberpsychol J Psychosoc Res Cybersp 7(3):6CrossRefGoogle Scholar
  28. Griskevicius V, Tybur JM, Delton AW, Robertson TE (2011) The influence of mortality and socioeconomic status on risk and delayed rewards: a life history theory approach. J Person Soc Psychol 100(6):1015CrossRefGoogle Scholar
  29. Hardoon DR, Szedmak S, Shawe-Taylor J (2004) Canonical correlation analysis: an overview with application to learning methods. Neural Comput 16(12):2639–2664CrossRefGoogle Scholar
  30. Hirsh J, Morisano D, Peterson J (2008) Adelay discounting: interactions between personality and cognitive ability. J Res Personal 42(6):1646–1650CrossRefGoogle Scholar
  31. Jaroni JL, Wright SM, Lerman C, Epstein LH (2004) Relationship between education and delay discounting in smokers. Addict Behav 29(6):1171–1175CrossRefGoogle Scholar
  32. Jing L, Tian Y (2019) Self-supervised visual feature learning with deep neural networks: a survey. CoRR arXiv:abs/1902.06162
  33. Johnson MW, Bickel WK (2002) Within-subject comparison of real and hypothetical money rewards in delay discounting. Exp Anal Behav 77(2):129–146CrossRefGoogle Scholar
  34. Jolliffe I (2002) Principal component analysis. Springer series in statistics. Springer, BerlinzbMATHGoogle Scholar
  35. Kirby K (1997) Bidding on the future: evidence against normative discounting of delayed rewards. Exp Psychol Gen 126(1):54–70CrossRefGoogle Scholar
  36. Kirby KN, Petry NM, Bickel WK (1999) Heroin addicts have higher discount rates for delayed rewards than non-drug-using controls. J Exp Psychol Gen 128(1):78CrossRefGoogle Scholar
  37. Kosinski M, Stillwell D, Graepel T (2013) Private traits and attributes are predictable from digital records of human behavior. Proc Natl Acad Sci 110(15):5802–5805CrossRefGoogle Scholar
  38. Kosinski M, Matz SC, Gosling SD, Popov V, Stillwell D (2015) Facebook as a research tool for the social sciences: opportunities, challenges, ethical considerations, and practical guidelines. Am Psychol 70(6):543CrossRefGoogle Scholar
  39. Kumar A, Daumé H (2011) A co-training approach for multi-view spectral clustering. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 393–400Google Scholar
  40. Lawrence JB, Stanford MS (1999) Impulsivity and time of day: effects on performance and cognitive tempo. Personal Individ Differ 25:199–207Google Scholar
  41. Le QV, Mikolov T (2014) Distributed representations of sentences and documents. In: ICML ,vol 14, pp 1188–1196Google Scholar
  42. Liao L, He X, Zhang H, Chua TS (2018) Attributed social network embedding. IEEE Trans Knowl Data Eng 30(12):2257–2270CrossRefGoogle Scholar
  43. Liu L, Preotiuc-Pietro D, Samani Z, Moghaddam M, Ungar L (2016) Analyzing personality through social media profile picture choice. In: ICWSM, pp 211–220Google Scholar
  44. Loewenstein G, Elster J (1992) Choice over time. Russell Sage Foundation, New YorkGoogle Scholar
  45. Madden G, Ewan E, Lagorio C (2007) Toward an animal model of gambling: delay discounting and the allure of unpredictable outcomes. J Gambl Studi 23(1):63–83CrossRefGoogle Scholar
  46. Mahalingam V, Stillwell D, Kosinski M, Rust J, Kogan A (1992) Who can wait for the future? A personality perspective. Soc Psychol Personal Sci 2(3):397–425Google Scholar
  47. Mikhail N, Koffarnus WKB (2014) A 5-trial adjusting delay discounting task: accurate discount rates in less than 60 seconds. Exp Clin Psychopharmacol 22:222CrossRefGoogle Scholar
  48. Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781
  49. Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111–3119Google Scholar
  50. Mischel W, Ebbesen E, Raskoff Zeiss A (1972) Cognitive and attentional mechanisms in delay of gratification. Personal Soc Psychol 21(2):204–218CrossRefGoogle Scholar
  51. Mischel W, Shoda Y, Rodriguzez M (1989) Delay of gratification in children. Science 244:933–938CrossRefGoogle Scholar
  52. O’Banion S, Birnbaum L (2013) Using explicit linguistic expressions of preference in social media to predict voting behavior. In: ASONAM. IEEE, pp 207–214Google Scholar
  53. Park G, Schwartz HA, Eichstaedt JC, Kern ML, Kosinski M, Stillwell DJ, Ungar LH, Seligman ME (2015) Automatic personality assessment through social media language. J Personal Soc Psychol 108(6):934CrossRefGoogle Scholar
  54. Patton JH, Stanford MS, Barratt ES (1995) Factor structure of the barratt impulsiveness scale. J Clinl Psychol 51(6):768–774CrossRefGoogle Scholar
  55. Pennacchiotti M, Popescu A (2011) A machine learning approach to twitter user classification. In: ICWSM, vol 11, no 1, pp 281–288Google Scholar
  56. Pennebaker JW, Booth RJ, Francis ME (2007) Linguistic inquiry and word count: Liwc [computer software]. Austin, TX: www.liwc.net
  57. Rachlin H, Raineri A, Cross D (1991) Subjective-probability and delay. J Exp Anal Behav 55(2):233–244CrossRefGoogle Scholar
  58. Sargin ME, Erzin E, Yemez Y, Tekalp AM (2006) Multimodal speaker identification using canonical correlation analysis. In: Acoustics, speech and signal processing, 2006. ICASSP 2006 proceedings. 2006 IEEE International Conference on, vol 1. IEEE, pp I–IGoogle Scholar
  59. Saville BK, Gisbert A, Kopp J, Telesco C (2010) Internet addiction and delay discounting in college students. Psychol Rec 60(2):273CrossRefGoogle Scholar
  60. Schlam T, Wilson N, Shoda Y, Mischel W, Ayduk O (2013) Preschoolers’ delay of gratification predicts their body mass 30 years later. Pediatrics 162:90–93CrossRefGoogle Scholar
  61. Schwartz HA, Eichstaedt JC, Kern ML, Dziurzynski L, Ramones SM, Agrawal M, Shah A, Kosinski M, Stillwell D, Seligman ME et al (2013) Personality, gender, and age in the language of social media: the open-vocabulary approach. PloS ONE 8(9):e73791CrossRefGoogle Scholar
  62. Schwartz HA, Eichstaedt JC, Kern ML, Dziurzynski L, Ramones SM, Agrawal M, Shah A, Kosinski M, Stillwell D, Seligman ME et al (2013) Personality, gender, and age in the language of social media: the open-vocabulary approach. PloS ONE 8(9):e73791CrossRefGoogle Scholar
  63. Shamosh NA, Gray JR (2008) Delay discounting and intelligence: a meta-analysis. Intelligence 36(4):289–305CrossRefGoogle Scholar
  64. Sharma A, Kumar A, Daume H, Jacobs DW (2012) Generalized multiview analysis: a discriminative latent space. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2160–2167Google Scholar
  65. Stanford MS, Mathias CW, Dougherty DM, Lake S, Anderson NE, Patton JH (2009) Fifty years of the barratt impulsiveness scale: an update and 31 review. Personal Individl Differ 47:385–395CrossRefGoogle Scholar
  66. Stillwell DJ, Tunney RJ (2012) Effects of measurement methods on the relationship between smoking and delay reward discounting. Addiction 107(5):1003–1012CrossRefGoogle Scholar
  67. Trunk GV (1979) A problem of dimensionality: a simple example. IEEE Trans Pattern Anal Mach Intell PAMI–1(3):306–307CrossRefGoogle Scholar
  68. Vedula N, Parthasarathy S (2017) Emotional and linguistic cues of depression from social media. In: Proceedings of the 2017 international conference on digital health. ACM, pp 127–136Google Scholar
  69. Weller RE, C EW III, Avsar KB, Cox JE (2008) Obese women show greater delay discounting than healthy-weight women. Appetite 51(3):563–569CrossRefGoogle Scholar
  70. Yang C, Pan S, Mahmud J, Yang H, Srinivasan P (2015) Using personal traits for brand preference prediction. In: EMNLP, pp 86–96Google Scholar
  71. Yano T, Cohen WW, Smith NA (2009) Predicting response to political blog posts with topic models. In: Proceedings of human language technologies: the 2009 annual conference of the North American chapter of the Association for Computational Linguistics. Association for Computational Linguistics, pp 477–485Google Scholar
  72. Youyou W, Kosinski M, Stillwell D (2015) Computer-based personality judgments are more accurate than those made by humans. In: Proceedings Of the national academy of sciences (PNAS)Google Scholar
  73. Zhang Z, Yang H, Bu J, Zhou S, Yu P, Zhang J, Ester M, Wang C (2018) ANRL: attributed network representation learning via deep neural networks. In: IJCAIGoogle Scholar
  74. Zhang D, Yin J, Zhu X, Zhang C (2017) User profile preserving social network embedding. In: IJCAIGoogle Scholar
  75. Zhou B, Lapedriza A, Xiao J, Torralba A, Oliva A (2014) Learning deep features for scene recognition using places database. In: Proceedings of the 27th international conference on neural information processing systems - Volume 1, NIPS’14, pp 487–495Google Scholar

Copyright information

© Springer-Verlag GmbH Austria, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Information SystemsUniversity of MarylandBaltimore CountyUSA
  2. 2.Addiction Recovery Research CenterVirginia Tech Carilion Research InstituteRoanokeUSA

Personalised recommendations